Skip to content
Fossfits
Index

Windows.

Projects with a maintained Windows build or WSL-friendly install path.

88 listedCatalog Sep 1, 2026

  1. Rank 1. llamafileSingle-file LLM runtime from Mozilla. Download, chmod, run.GitHub stars: 23k
  2. Rank 2. Gemini CLIGoogle’s Apache-2.0 terminal coding agent with MCP tools and a large free tier.GitHub stars: 107k
  3. Rank 3. gptmeMIT terminal agent toolkit with code, shell, and web tools — local-model friendly.GitHub stars: 4k
  4. Rank 4. GPT4AllNomic’s local chat app and model catalog for laptops without a GPU.GitHub stars: 76k
  5. Rank 5. text-generation-webuiGradio UI for local models with loaders, LoRA, and extensions.GitHub stars: 45k
  6. Rank 6. LiteLLMProxy that translates many model APIs into one OpenAI-shaped client.GitHub stars: 30k
  7. Rank 7. Stable Diffusion web UIThe AUTOMATIC1111 Gradio UI that made local SD mainstream.GitHub stars: 157k
  8. Rank 8. stable-diffusion.cppPure C/C++ inference for SD, Flux, and Qwen-Image weights — CPU included.GitHub stars: 7k
  9. Rank 9. Open-SoraApache-2.0 research stack for training and running video diffusion on 24 GB cards.GitHub stars: 30k
  10. Rank 10. KdenliveKDE non-linear editor with a deep effects and proxy workflow.GitHub stars: 4k
  11. Rank 11. OpenShotBeginner-friendly open-source video editor with animated titles.GitHub stars: 6.4k
  12. Rank 12. OliveModern open-source NLE aimed at professional timeline work.GitHub stars: 9k
  13. Rank 13. InvokeAIPolished local creative tool around diffusion, with a studio UI.GitHub stars: 26k
  14. Rank 14. FooocusMidjourney-like simplicity on top of local diffusion.GitHub stars: 46k
  15. Rank 15. WhisperOpenAI’s speech-to-text model you can run locally.GitHub stars: 90k
  16. Rank 16. LosslessCutFast lossless cut, trim, and remux without re-encoding.GitHub stars: 43k
  17. Rank 17. FlowiseLow-code node UI on top of LangChain-style flows.GitHub stars: 44k
  18. Rank 18. llama.cppC/C++ runtime that made local GGUF models practical.GitHub stars: 87k
  19. Rank 19. AnythingLLMDesktop and server chat with documents, agents, and many backends.GitHub stars: 49k
  20. Rank 20. KhojSelf-hostable AI second brain that searches your notes, docs, and the web.GitHub stars: 37k
  21. Rank 21. Open WebUISelf-hosted chat UI that sits on Ollama, OpenAI, or a local runner.GitHub stars: 111k
  22. Rank 22. KoboldCppOne-file llama.cpp build with a built-in chat UI aimed at offline storytelling.GitHub stars: 12k
  23. Rank 23. shell_gptCLI that runs an LLM as a shell command for scripts, refactors, and answers.GitHub stars: 12k
  24. Rank 24. Krita AI DiffusionKrita plugin that generates, inpaints, and outpaints as native layers via ComfyUI.GitHub stars: 11k
  25. Rank 25. JanDesktop ChatGPT-style app that runs models locally.GitHub stars: 38k
  26. Rank 26. OpenCodeOpen-source coding agent with a terminal UI, built to run against local or hosted models.GitHub stars: 42k
  27. Rank 27. OpenHandsSoftware agent that uses a sandbox to edit code, run tests, and open PRs.GitHub stars: 62k
  28. Rank 28. GooseBlock’s local-first agent runtime with a desktop and CLI.GitHub stars: 24k
  29. Rank 29. PiperFast local neural text-to-speech that runs on CPU.GitHub stars: 11k
  30. Rank 30. TabbySelf-hosted coding assistant with a local inference server.GitHub stars: 32k
  31. Rank 31. SurfSenseOpen NotebookLM-style researcher that crawls the live web and chats with your files.GitHub stars: 16k
  32. Rank 32. txtaiAll-in-one Python framework for embeddings, vector search, and RAG workflows.GitHub stars: 13k
  33. Rank 33. OllamaLocal model runner with a one-line CLI and a REST API.GitHub stars: 152k
  34. Rank 34. OpenAI Codex CLIOpen-source terminal coding agent from OpenAI that plans, edits, and tests repos in a sandbox.GitHub stars: 123k
  35. Rank 35. AiderTerminal pair programmer that edits a git repo and commits the result.GitHub stars: 37k
  36. Rank 36. Open InterpreterNatural-language computer use that runs code locally.GitHub stars: 61k
  37. Rank 37. LLaMA-FactoryWeb UI and YAML recipes for fine-tuning many open LLMs.GitHub stars: 58k
  38. Rank 38. QdrantRust vector database with filters, payloads, and a REST API.GitHub stars: 26k
  39. Rank 39. CrushCharmbracelet’s terminal coding agent with sessions, LSP context, and any model provider.GitHub stars: 28k
  40. Rank 40. DeepSpeedMicrosoft’s Apache-2.0 ZeRO optimizer for multi-GPU, multi-node LLM training.GitHub stars: 43k
  41. Rank 41. PhoenixLocal LLM tracing and evals workspace from Arize — pip install and open.GitHub stars: 11k
  42. Rank 42. LocalAIOpenAI-compatible API that can sit in front of several local backends.GitHub stars: 35k
  43. Rank 43. ClineVS Code agent that can use the editor, the terminal, and the browser.GitHub stars: 53k
  44. Rank 44. n8nSelf-hosted workflow automation with native AI nodes.GitHub stars: 150k
  45. Rank 45. PlandexTerminal agent that sandboxes and versions every change for big, long coding tasks.GitHub stars: 16k
  46. Rank 46. Stable Diffusion WebUI ForgeLeaner Stable Diffusion WebUI rework tuned for SDXL and Flux on modest GPUs.GitHub stars: 13k
  47. Rank 47. FaceFusionIndustry-leading face swap and enhancement pipeline with CLI and web UI.GitHub stars: 30k
  48. Rank 48. FramePackLong local image-to-video with a low VRAM floor.GitHub stars: 18k
  49. Rank 49. LTX-VideoLightricks open video model aimed at faster local clips.GitHub stars: 8k
  50. Rank 50. MochiGenmo’s Apache-2.0 10B video model — permissive weights, heavy hardware.GitHub stars: 3.7k
  51. Rank 51. SkyReels V1HunyuanVideo-based human-centric video model that fits one 24 GB GPU.GitHub stars: 2.7k
  52. Rank 52. ShortGPTMIT framework that automates short-form video from script to rendered clip.GitHub stars: 7.9k
  53. Rank 53. whisper.cppC/C++ port of Whisper for fast local transcription.GitHub stars: 45k
  54. Rank 54. Faster-WhisperWhisper reimplementation on CTranslate2 for faster local ASR.GitHub stars: 19k
  55. Rank 55. whisperXWhisper with word-level timestamps and speaker diarization for real subtitles.GitHub stars: 24k
  56. Rank 56. kokoro-onnxKokoro 82M voices as ONNX — real-time TTS on CPU with zero GPU.GitHub stars: 2.7k
  57. Rank 57. GPT-SoVITSFew-shot voice cloning and cross-lingual TTS with a full training WebUI.GitHub stars: 62k
  58. Rank 58. PrivateGPTApache-2.0 local RAG API layer for chatting with private documents offline.GitHub stars: 58k
  59. Rank 59. CSMSesame’s 1B conversational speech model behind the viral Maya voice demo.GitHub stars: 15k
  60. Rank 60. kotaemonApache-2.0 document chat with visible citations and RAG evaluation built in.GitHub stars: 26k
  61. Rank 61. LlamaIndexThe MIT Python framework for building document ingestion and RAG pipelines.GitHub stars: 52k
  62. Rank 62. QuivrSecond-brain RAG server with an API and client libraries for your own app.GitHub stars: 40k
  63. Rank 63. ChromaDeveloper-friendly embedding database for local RAG prototypes.GitHub stars: 23k
  64. Rank 64. LanceDBEmbedded serverless vector database — SQLite-style, multimodal, no server to run.GitHub stars: 11k
  65. Rank 65. FaissFacebook’s MIT ANN library for billion-scale embedding search on CPU or GPU.GitHub stars: 41k
  66. Rank 66. UnslothFaster LoRA fine-tuning with lower VRAM on consumer GPUs.GitHub stars: 45k
  67. Rank 67. TRLHugging Face’s Apache-2.0 trainers for SFT, DPO, PPO, and reward modeling.GitHub stars: 19k
  68. Rank 68. nanoGPTKarpathy’s ~300-line GPT trainer — the cleanest way to learn LLM training.GitHub stars: 63k
  69. Rank 69. AutomatischSelf-hosted no-code workflow builder — the direct open Zapier replacement.GitHub stars: 14k
  70. Rank 70. KestraApache-2.0 event-driven orchestration with YAML flows and a clean UI.GitHub stars: 28k
  71. Rank 71. SGLangFast model serving with KV-cache reuse for agent and reasoning workloads.GitHub stars: 36k
  72. Rank 72. XinferenceServe LLMs, embeddings, and media models from one Apache-2.0 platform.GitHub stars: 9.6k
  73. Rank 73. MLC-LLMCompile-and-serve LLMs on Metal, Vulkan, WebGPU, and phones — no CUDA required.GitHub stars: 23k
  74. Rank 74. ContinueOpen-source autocomplete and chat inside VS Code and JetBrains.GitHub stars: 29k
  75. Rank 75. ZedHigh-performance Rust editor with agent editing and live collaboration.GitHub stars: 90k
  76. Rank 76. ComfyUINode graph for diffusion workflows. The power-user default.GitHub stars: 91k
  77. Rank 77. SwarmUIMIT diffusion UI that swarms ComfyUI backends across all your GPUs.GitHub stars: 4.5k
  78. Rank 78. HunyuanVideoTencent’s 13B video generation model — top-tier motion, heavy VRAM needs.GitHub stars: 13k
  79. Rank 79. ShotcutCross-platform timeline editor with a gentle learning curve.GitHub stars: 15k
  80. Rank 80. CapOpen-source Loom alternative for shareable screen recordings.GitHub stars: 22k
  81. Rank 81. F5-TTSMIT flow-matching TTS with expressive multilingual voices at consumer-GPU speed.GitHub stars: 15k
  82. Rank 82. GraphRAGMicrosoft’s MIT library for graph-based RAG over whole document corpora.GitHub stars: 36k
  83. Rank 83. pgvectorVector similarity search as a Postgres extension — embeddings without a new database.GitHub stars: 23k
  84. Rank 84. MarqoDocker-deployed search engine combining vector and keyword search for discovery apps.GitHub stars: 5k
  85. Rank 85. PEFTHugging Face’s LoRA/QLoRA library that makes big-model tuning fit one GPU.GitHub stars: 22k
  86. Rank 86. Trigger.devApache-2.0 durable workflow engine for AI agents and background jobs in TypeScript.GitHub stars: 16k
  87. Rank 87. Node-REDThe veteran flow-based automation editor — drag nodes, wire events, deploy.GitHub stars: 24k
  88. Rank 88. TensorRT-LLMNVIDIA’s kernel-level serving stack for maximum GPU inference throughput.GitHub stars: 15k